openai
7.45.1 · 27 Oct 2026Apache-2.036.8M / weekRepositoryHomepagenpmAtom feed
7.45.1 is the newest release of 7.x.
In short
1 breaking1 new1 faster3 internal
- breaking
api: expand Live Decision item and question types. Breaking change in a minor release. Live Decision item events now include messages and function/custom-tool calls and outputs.
DecisionItemCreatedEvent.itemandDecisionItemCreateEvent.itemare unions, so callers that directly accessitem.contentoritem.rolemay no longer compile. For both event types, useif ('content' in event.item)before accessing message fields, and handle tool-item variants separately. Message items may omittype, so checking onlyitem.type === 'message'can skip valid messages. This release also updates image-model documentation:gpt-image-1was shut down on October 23, 2026; replace explicit selections withgpt-image-2.5-sunburstorgpt-image-2.5-flare. The documented default for Responses image-generation tools is nowgpt-image-2; specify a supported model explicitly when you need a particular model.
Release note
Features
api: add delegation controls and prompt cache lifetimes and scheduled automations via
client.beta.agents.automations, including invocation endpoints and theautomationsagent-tool variant- breaking
api: expand Live Decision item and question types. Breaking change in a minor release. Live Decision item events now include messages and function/custom-tool calls and outputs.
DecisionItemCreatedEvent.itemandDecisionItemCreateEvent.itemare unions, so callers that directly accessitem.contentoritem.rolemay no longer compile. For both event types, useif ('content' in event.item)before accessing message fields, and handle tool-item variants separately. Message items may omittype, so checking onlyitem.type === 'message'can skip valid messages. This release also updates image-model documentation:gpt-image-1was shut down on October 23, 2026; replace explicit selections withgpt-image-2.5-sunburstorgpt-image-2.5-flare. The documented default for Responses image-generation tools is nowgpt-image-2; specify a supported model explicitly when you need a particular model.
Performance Improvements
agents: reuse action checks between stream events